Stars
★ 10
MCP Server
Maintained
MPL-2.0
local
nangman-infra/touch-browser
Evidence-grounded web research for AI agents. Verifies page-local claims with citations, confidence bands, policy reports, and multi-page session synthesis via MCP.
Quality score 53/100
Last commit
1mo ago
Language
Rust
Install
Rust (cargo)
Category
Repository
Installation
Build from source (Rust)
git clone https://github.com/nangman-infra/touch-browser.git
cd touch-browser
cargo build --releaseRelated in Research
MCP Server
Active
mnemox-ai/idea-reality-mcp
Pre-build reality check for AI coding agents. Scans GitHub, Hacker News, npm, PyPI, and Product Hunt to detect existing competition before building, returning a reality signal score (0-100), duplicate likelihood, similar projects, and pivot hints.
MCP Server
Active
patsnap/patent-literature-search-mcp
Natural-language patent and scientific literature search across 200M+ patents and 216M+ papers from 170+ jurisdictions, with semantic/BM25 search, structured filters, and record retrieval. Hosted Streamable HTTP endpoint and Dockerized stdio bridge; requires a free Patsnap API key.
MCP Server
Active
yusong652/pfc-mcp
MCP server for [ITASCA PFC](https://www.itascacg.com/software/pfc) discrete element simulation — browse documentation, execute scripts, capture plots, and manage long-running tasks via a WebSocket bridge to the PFC GUI.
MCP Server
Active
WenyuChiou/research-hub
Research workspace MCP integrating Zotero, Obsidian, and NotebookLM. Search papers (arXiv/Semantic Scholar/PubMed/CrossRef), ingest into Zotero, sync notes to Obsidian, verify NotebookLM briefs. All three external tools optional. `pip install research-hub-pipeline` then `research-hub serve`.
MCP Server
Active
pminervini/deep-research-mcp
Deep research MCP server for OpenAI Responses API or Open Deep Research (smolagents), with web search and code interpreter support.
MCP Server
Active
BrowseAI-HQ/BrowserAI-Dev
Evidence-backed web research for AI agents. Real-time search with cited claims, confidence scores, and compare mode (raw LLM vs evidence-backed). MCP server, REST API, and Python SDK.